Evaluation of the impact of physical adversarial attacks on deep learning models for classifying covid cases

Erikson J. de Aguiar; Karem D. Marcomini; Felipe A. Quirino; Marco A. Gutierrez; Caetano Traina Jr.; Agma J. M. Traina

doi:10.1117/12.2611199

4 April 2022 Evaluation of the impact of physical adversarial attacks on deep learning models for classifying covid cases

Erikson J. de Aguiar, Karem D. Marcomini, Felipe A. Quirino, Marco A. Gutierrez, Caetano Traina Jr., Agma J. M. Traina

Author Affiliations +

Proceedings Volume 12033, Medical Imaging 2022: Computer-Aided Diagnosis; 120332P (2022) https://doi.org/10.1117/12.2611199
Event: SPIE Medical Imaging, 2022, San Diego, California, United States

Conference Poster

Abstract

The SARS-CoV-2 (COVID-19) disease rapidly spread worldwide, thus increasing the need to create new strategies to fight it. Several researchers in different fields have attempted to develop methods to early identifying it and mitigating its effects. The Deep Learning (DL) approach, such as the Convolutional Neural Networks (CNNs), has been increasingly used in COVID-19 diagnoses. These models intend to support decision-making and are doing well to detecting patient status early. Although DL models have good accuracy to support diagnosis, they are vulnerable to Adversarial Attacks. These attacks are new methods to make DL models biased by adding small perturbations on the original image. This paper investigates the impact of Adversarial Attacks on DL models for classifying X-ray images of COVID-19 cases. We focused on the attack Fast Gradient Sign Method (FGSM), which aims to add perturbations to the testing images by combining a perturbation matrix, producing a crafted image. We conduct the experiments analyzing the model’s performance attack-free and adding attacks. The following CNNs models were selected: DenseNet201, ResNet-50V2, MobileNetV2, NasNet and VGG16. In the attack-free environment, we reach precision around 99%. When it adds the attack, our results revealed that all models suffer from performance reduction, and the most affected was MobileNet that reduced its ability from 98.61% to 67.73%. However, the VGG16 network showed to be the least affected by the attacks. Our finds describe that DL models for COVID-19 are vulnerable to Adversarial Examples. The FGSM was capable of fooling the model, resulting in a significant reduction in the DL performance.

Citation Download Citation

Erikson J. de Aguiar, Karem D. Marcomini, Felipe A. Quirino, Marco A. Gutierrez, Caetano Traina Jr., and Agma J. M. Traina "Evaluation of the impact of physical adversarial attacks on deep learning models for classifying covid cases", Proc. SPIE 12033, Medical Imaging 2022: Computer-Aided Diagnosis, 120332P (4 April 2022); https://doi.org/10.1117/12.2611199

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available